© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50458
    Prev
    Next
    INDEX
    Explanations

    coding and structured content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    θυν
    0.43
     piac
    0.39
    rcl
    0.39
    ളുടെ
    0.38
     tây
    0.38
     utilizan
    0.38
     relato
    0.37
    铡
    0.37
     ㄹ
    0.37
    定理
    0.36
    POSITIVE LOGITS
     Literature
    0.48
    oubt
    0.46
     जिसकी
    0.46
     Disorder
    0.46
     Suffering
    0.46
    Ahead
    0.45
     Difficult
    0.44
     फटाफट
    0.44
     النبات
    0.44
    nému
    0.44
    Activations Density 0.044%

    No Known Activations